aws-advisor
Expert AWS Cloud Advisor for architecture design, security review, and implementation guidance. Leverages AWS MCP tools for accurate, documentation-backed answers. Use when user asks about AWS architecture, security, service selection, migrations, troubleshooting, or learning AWS. Triggers on AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway, or any AWS service. Do NOT use for non-AWS cloud providers or general infrastructure without AWS context.
89
86%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Advisory
Suggest reviewing before use
Quality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that covers all key dimensions well. It provides specific capabilities, comprehensive trigger terms spanning many AWS services, explicit 'Use when' and 'Do NOT use' clauses, and clear boundaries that distinguish it from other cloud-related skills. The third-person voice is used correctly throughout.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: 'architecture design, security review, and implementation guidance' along with specific use cases like 'migrations, troubleshooting, or learning AWS'. Also mentions leveraging AWS MCP tools for documentation-backed answers. | 3 / 3 |
Completeness | Clearly answers both 'what' (architecture design, security review, implementation guidance with MCP tools) and 'when' (explicit 'Use when' clause with triggers, plus a 'Do NOT use' exclusion clause for non-AWS contexts). | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms users would say: 'AWS, Lambda, S3, EC2, ECS, EKS, DynamoDB, RDS, CloudFormation, CDK, Terraform, Serverless, SAM, IAM, VPC, API Gateway' plus broader terms like 'architecture', 'security', 'migrations', 'troubleshooting'. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with a clear niche (AWS-specific cloud advisory) and explicit boundary setting via the 'Do NOT use for non-AWS cloud providers' clause, which reduces conflict risk with other cloud or infrastructure skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
72%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured AWS advisor skill with strong actionability through concrete tool mappings, search topic selection guides, and executable IaC examples. Its main weaknesses are some verbosity in areas where Claude already has knowledge (IaC syntax, general consulting principles) and workflows that lack validation checkpoints and error recovery paths. The progressive disclosure pattern with reference files and scripts is exemplary.
Suggestions
Add validation/error handling steps to workflows (e.g., 'If search returns no results, broaden topic to general' or 'If script fails, check architecture description format')
Trim or remove the IaC code examples section—Claude already knows these syntaxes; instead, just specify 'provide examples in user's preferred IaC tool' and focus on AWS-specific patterns Claude wouldn't know
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally well-structured with tables for efficiency, but includes some unnecessary content like explaining when to use each IaC tool (Claude can reason about this), and the IaC code examples are somewhat redundant given Claude already knows these syntaxes. The 'Core Principles' and 'Response Style' sections contain generic advice Claude already follows. | 2 / 3 |
Actionability | Provides concrete MCP tool names with specific use cases, executable code examples across multiple IaC tools, specific search topic mappings, and references to runnable scripts. The guidance is specific enough to act on immediately. | 3 / 3 |
Workflow Clarity | Workflows are listed with clear sequences (Standard Question Flow, Architecture Review, Security Review), but they lack validation checkpoints and error recovery steps. For example, what happens if a search returns no results? What if a script fails? No feedback loops are defined. | 2 / 3 |
Progressive Disclosure | Excellent use of progressive disclosure with a clear 'Reference Files' table that specifies when to load each file, scripts separated from main content, and well-organized sections using tables for quick scanning. References are one level deep and clearly signaled. | 3 / 3 |
Total | 10 / 12 Passed |
Validation
100%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- tech-leads-club/agent-skills
- Commit
81e7e0d
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.